monoxgas

nanoGPT

The simplest, fastest repository for training/finetuning medium-sized GPTs.

minGPT

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

unsloth

Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

mercury

Convert Jupyter Notebooks to Web Apps

napkin-math

Techniques and numbers for estimating system's performance from first-principles

toolong

A terminal application to view, tail, merge, and search log files (plus JSONL).

opyrator

🪄 Turns your machine learning code into microservices with web API, interactive GUI, and more.

docarray

Represent, send, store and search multimodal data

BadBlood

BadBlood by @davidprowe, Secframe.com, fills a Microsoft Active Directory Domain with a structure and thousands of objects. The output of the tool is a domain similar to a domain in the real world. After BadBlood is ran on a domain, security analysts and engineers can practice using tools to gain an understanding and prescribe to securing Active Directory. Each time this tool runs, it produces different results. The domain, users, groups, computers and permissions are different. Every. Single. Time.

aici

AICI: Prompts as (Wasm) Programs

schedule_free

Schedule-Free Optimization in PyTorch

distilabel

Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verified research papers.

priompt

Prompt design using JSX.

puncia

The Panthera(P.)uncia of Cybersecurity - Official CLI utility for Subdomain Center & Exploit Observer.

Platypus

A Free and Open Source Python Library for Multiobjective Optimization

binder-trace

Binder Trace is a tool for intercepting and parsing Android Binder messages. Think of it as "Wireshark for Binder".

repeng

A library for making RepE control vectors

Consistency_LLM

[ICML 2024] CLLMs: Consistency Large Language Models

tree-math

Mathematical operations for JAX pytrees

rigging

Lightweight LLM Interaction Framework

llm-adaptive-attacks

Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [arXiv, Apr 2024]

Monocle

Tooling backed by an LLM for performing natural language searches against compiled target binaries. Search for encryption logic, password strings, vulnerabilities, etc.

sasori

Sasori is a dynamic web crawler powered by Puppeteer, designed for lightning-fast endpoint discovery.

magikarp

advprompter

Official implementation of AdvPrompter https//arxiv.org/abs/2404.16873

challenge-001-exemplar

Challenge Problem #1 - Linux Kernel (NOTE: This code does not reflect the active state of what will be used at competition time, please refer to resources inside of the competition environment)

esorm

Python ElasticSearch ORM based on Pydantic

paperstack

Arxiv + Notion Sync

challenge-001-exemplar-source

Challenge Problem #1 - Linux Kernel Source (NOTE: This code does not reflect the active state of what will be used at competition time, please refer to resources inside of the competition environment)

bad_lemon

Experiments with faster black box adversarial attacks